Downloads · 30 days
25
25% of all-time downloads
SeaWolf-AI/Darwin-Qwen3.5-27B-x-Qwen3.5-27B-Claude-4-08162
Darwin-Qwen3.5-27B-x-Qwen3.5-27B-Claude-4-08162 is a machine learning model from SeaWolf-AI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Created by Darwin V6 diagnostic-guided evolutionary merge engine.
Downloads · 30 days
25
25% of all-time downloads
All-time downloads
100
Public
Parameters
27.8B
55.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors55.6 GB · 100%
From the Hugging Face model README
Created by Darwin V6 diagnostic-guided evolutionary merge engine.
Qwen/Qwen3.5-27BJackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled global_ratio: 0.4893
attn_ratio: 0.1463
ffn_ratio: 0.8768
embed_ratio: 0.3021
density_a: 0.8507
density_b: 0.9413
block_0_ratio: 0.6750
block_1_ratio: 0.4790
block_2_ratio: 0.3610
block_3_ratio: 0.4365
block_4_ratio: 0.5255
block_5_ratio: 0.6525
block_6_ratio: 0.5557
block_7_ratio: 0.2783
block_8_ratio: 0.7302
block_9_ratio: 0.4764
mri_trust: 0.8571
merge_method_weight: 0.7802
failed: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/data/ray_temp/ginipick/darwin_merge_cache/merged_9cd05ed7'. Use repo_type argument if needed.
Darwin V6 implements DARE-TIES merge directly via PyTorch tensor operations. Per-tensor ratios are determined by MRI diagnostic (static tensor analysis + probe-based functional importance) combined with evolutionary genome search.
Formula: final_ratio = mri_ratio * mri_trust + genome_ratio * (1 - mri_trust)
DARE-TIES algorithm: Yadav et al., 2023 (re-implemented, not library-dependent)
Built by VIDRAFT. Apache 2.0.